29 citations · 69 across the 20 of their papers we have counts for
22 papers
InternW0-: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data
Xingyu Miao, Zizun Li, Baole Fang +45
World Action Models (WAMs) jointly model visual dynamics and action generation for generalist robot manipulation. A central challenge is to integrate priors from large-scale pretra…
From Alignment to Fusion in 3D Vision-Language
Xueqi Qiu, Xingyu Miao, Jingjing Deng +3
Unified 3D vision-language systems must combine complementary geometry, scale, and appearance cues while supporting tasks from instance segmentation to language-guided reasoning. E…
M2StyleGS: Multi-Modality 3D Style Transfer with Gaussian Splatting
Xingyu Miao, Xueqi Qiu, Haoran Duan +4
Conventional 3D style transfer methods rely on a fixed reference image to apply artistic patterns to 3D scenes. However, in practical applications such as virtual or augmented real…
TrajVG: 3D Trajectory-Coupled Visual Geometry Learning
Xingyu Miao, Weiguang Zhao, Tao Lu +5
Feed-forward multi-frame 3D reconstruction models often degrade on videos with object motion. Global-reference becomes ambiguous under multiple motions, while the local pointmap re…
SynthVerse: A Large-Scale Diverse Synthetic Dataset for Point Tracking
Weiguang Zhao, Haoran Xu, Xingyu Miao +11
Point tracking aims to follow visual points through complex motion, occlusion, and viewpoint changes, and has advanced rapidly with modern foundation models. Yet progress toward ge…
From Frames to Sequences: Temporally Consistent Human-Centric Dense Prediction
Xingyu Miao, Junting Dong, Qin Zhao +3
In this work, we focus on the challenge of temporally consistent human-centric dense prediction across video sequences. Existing models achieve strong per-frame accuracy but often…
vMFCoOp: Towards Equilibrium on a Unified Hyperspherical Manifold for Prompting Biomedical VLMs
Minye Shao, Sihan Guo, Xinrun Li +3
Recent advances in context optimization (CoOp) guided by large language model (LLM)-distilled medical semantic priors offer a scalable alternative to manual prompt engineering and…
LongCat-Flash Technical Report
Meituan LongCat Team, Bayan, Bei Li +179
We introduce LongCat-Flash, a 560-billion-parameter Mixture-of-Experts (MoE) language model designed for both computational efficiency and advanced agentic capabilities. Stemming f…
Decoding Visual Neural Representations by Multimodal with Dynamic Balancing
Kaili sun, Xingyu Miao, Bing Zhai +2
In this work, we propose an innovative framework that integrates EEG, image, and text data, aiming to decode visual neural representations from low signal-to-noise ratio EEG signal…
Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting
Xingyu Miao, Haoran Duan, Quanhao Qian +6
Spatial intelligence is emerging as a transformative frontier in AI, yet it remains constrained by the scarcity of large-scale 3D datasets. Unlike the abundant 2D imagery, acquirin…
TRACE: Temporally Reliable Anatomically-Conditioned 3D CT Generation with Enhanced Efficiency
Minye Shao, Xingyu Miao, Haoran Duan +7
3D medical image generation is essential for data augmentation and patient privacy, calling for reliable and efficient models suited for clinical practice. However, current methods…
Rethinking Score Distilling Sampling for 3D Editing and Generation
Xingyu Miao, Haoran Duan, Yang Long +1
Score Distillation Sampling (SDS) has emerged as a prominent method for text-to-3D generation by leveraging the strengths of 2D diffusion models. However, SDS is limited to generat…
Attention in Diffusion Model: A Survey
Litao Hua, Fan Liu, Jie Su +9
Attention mechanisms have become a foundational component in diffusion models, significantly influencing their capacity across a wide range of generative and discriminative tasks.…
D2Fusion: Dual-domain Fusion with Feature Superposition for Deepfake Detection
Xueqi Qiu, Xingyu Miao, Fan Wan +5
Deepfake detection is crucial for curbing the harm it causes to society. However, current Deepfake detection methods fail to thoroughly explore artifact information across differen…
Asynchronous Personalized Federated Learning through Global Memorization
Fan Wan, Yuchen Li, Xueqi Qiu +6
The proliferation of Internet of Things devices and advances in communication technology have unleashed an explosion of personal data, amplifying privacy concerns amid stringent re…
Laser: Efficient Language-Guided Segmentation in Neural Radiance Fields
Xingyu Miao, Haoran Duan, Yang Bai +5
In this work, we propose a method that leverages CLIP feature distillation, achieving efficient 3D segmentation through language guidance. Unlike previous methods that rely on mult…
ExactDreamer: High-Fidelity Text-to-3D Content Creation via Exact Score Matching
Yumin Zhang, Xingyu Miao, Haoran Duan +4
Text-to-3D content creation is a rapidly evolving research area. Given the scarcity of 3D data, current approaches often adapt pre-trained 2D diffusion models for 3D synthesis. Amo…
Dreamer XL: Towards High-Resolution Text-to-3D Generation via Trajectory Score Matching
Xingyu Miao, Haoran Duan, Varun Ojha +4
In this work, we propose a novel Trajectory Score Matching (TSM) method that aims to solve the pseudo ground truth inconsistency problem caused by the accumulated error in Interval…
Sentinel-Guided Zero-Shot Learning: A Collaborative Paradigm without Real Data Exposure
Fan Wan, Xingyu Miao, Haoran Duan +3
With increasing concerns over data privacy and model copyrights, especially in the context of collaborations between AI service providers and data owners, an innovative SG-ZSL para…
ConRF: Zero-shot Stylization of 3D Scenes with Conditioned Radiation Fields
Xingyu Miao, Yang Bai, Haoran Duan +4
Most of the existing works on arbitrary 3D NeRF style transfer required retraining on each single style condition. This work aims to achieve zero-shot controlled stylization in 3D…
CTNeRF: Cross-Time Transformer for Dynamic Neural Radiance Field from Monocular Video
Xingyu Miao, Yang Bai, Haoran Duan +4
The goal of our work is to generate high-quality novel views from monocular videos of complex and dynamic scenes. Prior methods, such as DynamicNeRF, have shown impressive performa…
DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume
Xingyu Miao, Yang Bai, Haoran Duan +5
Self-supervised monocular depth estimation methods typically rely on the reprojection error to capture geometric relationships between successive frames in static environments. How…